Enhancing AV Safety with LiDAR in Snowy Conditions

Studies on autonomous driving have started to focus on snowy environments, and studies to acquire data and remove noise and pixels caused by snowfall in such environments are in progress. However, research to determine the necessary weather information for the control of unmanned platforms by sensing the degree of snowfall in real time has not yet been conducted. Therefore, in this study, we attempted to determine snowfall information for autonomous driving control in snowy weather conditions.

From a paper by Ji-il Park, et al.

To this end, snowfall data were acquired by LiDAR sensors in various snowy areas in South Korea, Sweden, and Denmark. Snow, which was extracted using a snow removal filter (the LIOR filter that we previously developed), was newly classified and defined based on the extracted number of snow particles, the actual snowfall total, and the weather forecast at the time.

Finally, we developed an algorithm that extracts only snow in real time and then provides snowfall information to an autonomous driving system. This algorithm is expected to have a similar effect to that of actual controllers in promoting driving safety in real-time weather conditions.

When a person drives a car, driving under snowy conditions is bound to be different from driving on a clear day. This is because people drive safely with an instinctive intuition due to limited vision, slippery roads, and short braking distances when it snows. Therefore, to implement fully autonomous driving on the ground, it is essential to recognize the weather environment in the same way as humans and drive safely based on it because the driving pattern varies depending on the weather [1].

However, because the currently developed unmanned vehicles, ships, drones, etc., cannot check real-time weather conditions as humans can, such safe autonomous driving control is virtually impossible. Currently, self-driving research is mainly focused on sunny weather, and even related technological development is limited.

With self-driving vehicles, the most representative platform among self-driving platforms, as an example, the autonomous driving levels can be divided into six classes, and the current level is level 3 or 4. Some companies, such as Hyundai, Waymo, and Cruise, claim that they have achieved level 4 autonomous driving [2,3,4]. However, this achievement is questionable because the current technology has only been applied in some limited environments. Regardless, level 4 autonomous driving is clearly on the verge of completion and will be achieved soon.

For the complete article CLICK HERE.